首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51013--1)

基于压缩感知与SURF特征的手语关键帧提取算法

Key Frame Extraction Algorithm of Sign Language Based on Compressed Sensing and SURF Features

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对实时、大词汇集、连续的手语视频高效准确地识别,提出了一种基于压缩感知与加速稳健特征(SURF)的手语关键帧提取算法。利用压缩感知将手语视频降维成低维多尺度帧图像特征,通过自适应阈值完成子镜头分割,以处理大量的手语帧数据;运用SURF特征点完成特征匹配,绘制其间的相似度曲线进而提取关键帧。在前期预处理阶段,采用基于HSV空间自适应颜色检测提取手势区域。实验验证,由本文算法提取到的关键帧具有较高的准确性,且算法具备处理大量复杂数据的能力。

Abstract

A key frame extraction algorithm of sign language based on compressed sensing and speed up robust features(SURF) feature is proposed to recognize the real-time, large vocabulary sets and continuous sign language videos efficiently and accurately. The sign language videos are reduced to the image features of low dimensional and multi-scale frame with compressed sensing. The segmentation of sub lens is completed by a adaptive threshold value, and a large number of sign language frame data are processed. We use SURF feature points to complete the feature matching, and the SURF frame similarity curve is drawn for extracting the key frames. In the pre-processing stage, we use the HSV space adaptive color detection to abstract the sign language area. Experimental results show that the key frames extracted by the proposed algorithm have high accuracy, and the proposed algorithm has the ability to process large amounts of complex data.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.411

DOI:10.3788/lop55.051013

所属栏目:图像处理

基金项目:住房和城乡建设部科学技术项目计划(2016-R2-045)、陕西省自然科学基础研究资金(2014JM8343)、陕西省自然科学基金青年基金(2013JQ8003)

收稿日期:2017-12-19

修改稿日期:2018-02-07

网络出版日期:--

作者单位    点击查看

王民:西安建筑科技大学信息与控制工程学院, 陕西 西安 710055
李泽洋:西安建筑科技大学信息与控制工程学院, 陕西 西安 710055
王纯:西安建筑科技大学信息与控制工程学院, 陕西 西安 710055
石新源:西安建筑科技大学信息与控制工程学院, 陕西 西安 710055

联系人作者:李泽洋(zenolzy@163.com)

备注:王民(1959—),男,本科,教授,硕士生导师,主要从事数字语音处理、多媒体通信技术等方面的研究。E-mail: wangmin1329@163.com

【1】Maraqa M, Al-Zboun F, Dhyabat M, et al. Recognition of arabic sign language (ArSL) using recurrent neural networks[J]. Journal of Intelligent Learning Systems and Applications, 2012, 4: 41-52.

【2】Sarkar A R, Sanyal G, Majumder S. Hand gesture recognition systems: a survey[J]. International Journal of Computer Applications, 2013, 71(15): 26-37.

【3】Samantaray A, Nayak S K, Mishra A K. Hand gesture recognition using computer vision[J]. International Journal of Scientific & Engineering Research, 2013, 4(6): 1602-1608.

【4】Liu W, Zhao W J, Li C. Long-term visual tracking based on spatio-temporal context[J]. Acta Optica Sinica, 2016, 36(1):0115001.
刘威, 赵文杰, 李成. 时空上下文学习长时目标跟踪[J]. 光学学报, 2016, 36(1): 0115001.

【5】Shen Q, Yan X L, Liu L F, et al. A scale adaptive correlation filtering tracker based on adaptive feature selection[J]. Acta Optica Sinica, 2017, 37(5): 0515001.
沈秋, 严小乐, 刘霖枫, 等. 基于自适应特征选择的多尺度相关滤波跟踪[J]. 光学学报, 2017, 37(5): 0515001.

【6】Li S R, Huang Y Y, Hu Z J, et al. Effective algorithm of key frame detection from dynamic sign language video[J]. Journal of Chinese Computer Systems, 2015, 36(7): 1597-1601.
李姝蓉, 黄元元, 胡作进, 等. 非特定人群动态手语视频中的关键帧检测算法[J]. 小型微型计算机系统, 2015, 36(7): 1597-1601.

【7】The Department for Education and Employment of China Disabled Persons′ Federation, China Association if the Deaf and Hard of Hearing. Chinese sign language[M].Beijing:Huaxia Publishing House, 2003.
中国残疾人联合会教育就业部, 中国聋人协会.中国手语[M]. 北京: 华夏出版社, 2003.

【8】Shih H C. Anovel attention-based key-frame determination method[J]. IEEE Transactions on Broadcasting, 2013, 59(3): 556-562.

【9】Hao H F. Key technology research of video shot segmentation and key frame extraction[D]. Wuhan: Central China Normal University, 2015.
郝会芬. 视频镜头分割和关键帧提取关键技术研究[D]. 武汉: 华中师范大学, 2015.

【10】Zhou W Z, Chen G L, Du S S, et al. Animproved iterative closest point algorithm using clustering[J]. Laser & Optoelectronics Progress, 2016, 53(5): 051202.
周文振, 陈国良, 杜珊珊, 等. 一种聚类改进的迭代最近点配准算法[J]. 激光与光电子学进展, 2016, 53(5): 051202.

【11】Zhong X, Yang G, Lu Y S. Method of key frames extraction based on double-threshold values sliding window sub-shot segmentation and fully connected graph[J]. Computer Science, 2016, 43(6): 289-293.
钟忺, 杨光, 卢炎生. 基于双阈值滑动窗口子镜头分割和完全连通图的关键帧提取方法[J]. 计算机科学, 2016, 43(6): 289-293.

【12】Nagesh P, Li B X. A compressive sensing approach for expression-invariant face recognition[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2009: 1518-1525.

【13】Bay H, Ess A,Ess A, Tuytelaars T, et al.Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

【14】Yang Q, Peng J Y. Chinesesign language recognition method based on depth image information and SURF-BoW[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(8): 741-749.
杨全, 彭进业. 基于深度信息和SURF-BoW的中国手语识别算法[J]. 模式识别与人工智能, 2014, 27(8): 741-749.

【15】Bao J T, Song A G, Guo Y, et al. Dynamic hand gesture recognition based on SURF tracking[J]. Robot, 2011, 33(4): 482-489.
包加桐, 宋爱国, 郭晏, 等. 基于SURF特征跟踪的动态手势识别算法[J]. 机器人, 2011, 33(4): 482-489.

【16】Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001: 511-518.

【17】Zhang Z L, Xue J, Qiao H H, et al. The vehicle retrieval method of traffic video based on improved SURF algorithm[J]. Journal of Northwestern Polytechnical University, 2014, 32(2): 297-302.
张子龙, 薛静, 乔鸿海, 等. 基于改进SURF算法的交通视频车辆检索方法研究[J]. 西北工业大学学报, 2014, 32(2): 297-302.

【18】Liu B, Zhao X, Hu C H, et al. Gesture recognition method of hand over face occlusion in color and depth images[J]. Laser & Optoelectronics Progress, 2016, 53(6): 061001.
刘斌, 赵兴, 胡春海, 等. 面向颜色深度图像手脸近距遮挡的手势识别[J]. 激光与光电子学进展, 2016, 53(6): 061001.

【19】Huang S Y, Liu Z Y, Ruan T Y. Algorithm of license extraction based on HSV color space and SVM[J]. Computer Systems & Applications, 2014, 23(8): 150-153.
黄社阳, 刘智勇, 阮太元. 基于HSV颜色空间和SVM的车牌提取算法[J]. 计算机系统应用, 2014, 23(8): 150-153.

【20】Pan L, Shu X, Cheng K, et al. A key frame extraction algorithm based on compressive sensing and entropy computing[J]. Journal of Optoelectronics·Laser, 2014, 25(10): 1977-1982.
潘磊, 束鑫, 程科, 等. 基于压缩感知和熵计算的关键帧提取算法[J]. 光电子·激光, 2014, 25(10): 1977-1982.

【21】Athani S, Tejeshwar C H. Performance analysis of key frame extraction using SIFT and SURF algorithms[J]. International Journal of Computer Science and Information Technologies, 2016, 7(4): 2136-2139.

【22】Grycuk R, Knop M, Mandal S, Video key frame detection based on SURF algorithm[C]. International Conference on Artificial Intelligence and Soft Computing, 2015: 566-576.

【23】Zhuang Y T, Rui Y, Huang T S, et al. Adaptive key frame extraction using unsupervised clustering[C]∥Proceedings International Conference on Image Processing, 1998, 2: 866-870.

引用该论文

Wang Min,Li Zeyang,Wang Chun,Shi Xinyuan. Key Frame Extraction Algorithm of Sign Language Based on Compressed Sensing and SURF Features[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051013

王民,李泽洋,王纯,石新源. 基于压缩感知与SURF特征的手语关键帧提取算法[J]. 激光与光电子学进展, 2018, 55(5): 051013

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF